Skip to main content
Glama

upload_data

Uploads a local responses file (CSV long format or Sawtooth .CHO for CBC) with an optional CBC design JSON, then returns the dataset ID and validation report so errors can be fixed before fitting.

Instructions

Upload a responses file from the local disk (CSV in the module's long format, or a Sawtooth .CHO for CBC; see api_reference for formats). Optional design JSON for CBC. Returns the dataset: its id, the validation report (errors must be fixed before fitting; read warnings) and, for CBC, the design (check design_inferred).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "responses_path": "<responses_path>"
    },
    "name": "upload_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
project_idYes
design_pathNo
responses_pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full behavioral burden and does a reasonable job: it discloses that it reads from local disk, that a validation report is returned, that errors block fitting, that warnings should be read, and that CBC designs should be checked for design_inferred. It does not cover overwrite/idempotency behavior (does re-uploading replace an existing dataset?), size limits, or permission requirements, which are real gaps for a write-side tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The action and its accepted inputs are front-loaded in the first sentence, with the return contract following. It is a dense multi-clause paragraph but nearly every clause carries information; the parenthetical cross-reference to api_reference is a minor detour but earns its place by avoiding format duplication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description supplies the return shape (dataset id, validation report, design) and the downstream consequence of validation errors, which is the key thing an agent needs to chain into fitting. The remaining gap is the undefined project_id parameter and unstated behavior on re-upload, which keep it short of full completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it partially does: responses_path is explained via the accepted formats and design_path is explained as optional design JSON for CBC. project_id is never mentioned, leaving one of three parameters — and a required one — entirely undefined beyond its name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Upload a responses file from the local disk') and immediately scopes the accepted formats (CSV long format, Sawtooth .CHO for CBC, optional design JSON). The return contract (dataset id, validation report, design) further pins down what the tool does, so an agent can distinguish it from download/get_dataset siblings without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: 'errors must be fixed before fitting' tells the agent this is a pre-fit step, and 'check design_inferred' tells it how to react to CBC results. There is no explicit statement of when to use this versus an alternative (e.g. get_dataset for already-uploaded data) or any exclusion, so guidance is inferential rather than directive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.